Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/bobbyjohnstx/tinycode/teamnpx skills add bobbyjohnstx/tinycode --skill teamgit clone --depth 1 https://github.com/bobbyjohnstx/tinycodeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00014 | $0.00928 |
| Opus 5 | $0.00007 | $0.00464 |
| Sonnet 5 | $0.00003 | $0.00186 |
| Haiku 4.5 | $0.00001 | $0.00093 |
Grade A, and why
team scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team — Multi-Agent Parallel Execution
Launch multiple tinycode worker sessions to tackle a task in parallel using the oh-my-tiny coordinator.
When to use
- The task has clearly separable subtasks (different files, different features, different investigations)
- A single agent would benefit from parallelism (e.g., implement N independent modules, run N searches)
- You want to fan out work and collect results
Worker count guidance
- 2 workers: default for most tasks; low overhead, good parallelism
- 3–4 workers: larger fan-outs (e.g., implement 4 independent features)
- Avoid 5+: each worker is a full tinycode session; more workers = more context window usage and coordination cost
Each worker has access to the full tinycode tool set (file read/write/edit, shell, grep, glob, LSP, etc.).
Mode 1: HTTP API mode (preferred)
Use this when the tinycode server is already running on port 4096. Workers become tinycode sessions driven via the HTTP API. This is the default and recommended approach.
node /Users/bjohns/projects/tinycode/node_modules/oh-my-tiny/dist/team/coordinator.js \
--server-url http://localhost:4096 \
--team <team-name> \
--workers <count> \
--task "<task description>" \
--cwd <project-directory>
Example
node /Users/bjohns/projects/tinycode/node_modules/oh-my-tiny/dist/team/coordinator.js \
--server-url http://localhost:4096 \
--team refactor-team \
--workers 3 \
--task "Refactor the three provider modules (ollama, openai, anthropic) to use the new BaseProvider interface. Each worker takes one module." \
--cwd /Users/bjohns/projects/tinycode
TASK_DONE protocol
In HTTP API mode, each worker signals completion by including one of these tokens in its final response:
TASK_DONE:taskId:success— worker completed successfullyTASK_DONE:taskId:failed— worker encountered an unrecoverable error
The coordinator monitors these signals to know when all workers are finished and to aggregate results.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 115 lines · 14 tokens per session scan A 70a39d627da4
team is a skill published in the GitHub repository bobbyjohnstx/tinycode (11 stars, last pushed 4d ago), licensed MIT. It adds 14 tokens to every session and 928 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
archon-cli
Drive Archon through its CLI: run AI workflows on a repo, manage those runs (inspect, approve, reject, cancel, resume), set up Archon or change its config, author new workflows, and improve workflow prompts. Use when the user says "use archon", "run archon", "archon workflow", "fix issue #N with archon", "have archon…
semantic-compression
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…
greet
A greeting skill for testing.